jakal 0.0.7

data/lib/jkl/rest_client.rb

@@ -0,0 +1,36 @@
+require 'net/http' 
+require 'hpricot'
+
+module Jkl
+  
+  def self.post_to(uri, post_args)
+    begin
+      resp, data = Net::HTTP.post_form(uri, post_args)
+      data
+    rescue  URI::InvalidURIError => e
+      puts("WARN: Invalid URI: #{e}")
+    rescue SocketError => e
+      puts("WARN: Could not connect: #{e}")
+    rescue Errno::ECONNREFUSED  => e
+      puts("WARN: Connection refused: #{e}")
+    end
+  end
+  
+  def self.get_from(uri)
+    begin
+      res = Net::HTTP.get_response(URI.parse(uri))
+      res.body
+    rescue  URI::InvalidURIError => e
+      puts("WARN: Invalid URI: #{e}")
+    rescue SocketError => e
+      puts("WARN: Could not connect: #{e}")
+    rescue Errno::ECONNREFUSED  => e
+      puts("WARN: Connection refused: #{e}")
+    end
+  end
+  
+  def self.get_from_as_xml(uri)
+    Hpricot.XML get_from uri
+  end
+  
+end

data/lib/jkl/rss_client.rb

@@ -0,0 +1,15 @@
+require 'hpricot'
+
+module Jkl
+  
+  def self.get_items_from(rssdoc)
+    items = []
+    (rssdoc/:item).each { |rssitem| items.push rssitem } unless rssdoc==nil
+    items
+  end
+  
+  def self.attribute_from(item, name)
+    (item/name).inner_html
+  end
+  
+end

data/lib/jkl/url_doc_handler.rb

@@ -0,0 +1,31 @@
+require 'hpricot'
+require 'rest_client'
+
+module Jkl
+  
+  def self.sanitize(text)
+    str = ""
+    text = text.to_s.gsub(/((<[\s\/]*script\b[^>]*>)([^>]*)(<\/script>))/i,"") #remove script tags - with contents
+    text.to_s.gsub(/<\/?[^>]*>/, "").split("\r").each do |l| # remove all tags
+      l = l.gsub(/^[ \t]/,"") #remove tabs
+      l = l.gsub(/^[ \s]/,"")
+      l.split("\n").each do |l|
+        str << l unless l.count(" ") < 5 # remove short lines - ususally just navigation
+      end
+    end
+    str
+  end
+  
+  def self.from_doc(response)
+    begin
+      Hpricot(response)
+    rescue  URI::InvalidURIError => e
+      puts("WARN: Problem with getting a connection: #{e}")
+    rescue SocketError => e
+      puts("WARN: Could not connect to feed: #{e}")
+    rescue Errno::ECONNREFUSED  => e
+      puts("WARN: Connection refused: #{e}")
+    end
+  end
+  
+end

metadata

@@ -0,0 +1,78 @@
+--- !ruby/object:Gem::Specification 
+name: jakal
+version: !ruby/object:Gem::Version 
+  version: 0.0.7
+platform: ruby
+authors: 
+- sshingler
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-08-27 00:00:00 +01:00
+default_executable: 
+dependencies: []
+
+description: Jakal is a Ruby library for dealing with information overload.
+email: "'shingler@gmail.com'"
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- README.rdoc
+- License.txt
+files: 
+- lib/jkl.rb
+- lib/jkl/calais_client.rb
+- lib/jkl/rest_client.rb
+- lib/jkl/rss_client.rb
+- lib/jkl/url_doc_handler.rb
+- features/calais.feature
+- features/http.feature
+- features/processing.feature
+- features/sanitize-text.feature
+- features/mocks/bbc_story.html
+- features/mocks/calais.json
+- features/mocks/topix_rss.xml
+- features/mocks/twitter.json
+- features/step_definitions/calais_steps.rb
+- features/step_definitions/http_steps.rb
+- features/step_definitions/processing_steps.rb
+- features/step_definitions/require_steps.rb
+- features/step_definitions/sanitize-text_steps.rb
+- features/step_definitions/twitter_steps.rb
+- features/support/env.rb
+- README.rdoc
+- License.txt
+has_rdoc: true
+homepage: http://github.com/sshingler/jkl
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --inline-source
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.5
+signing_key: 
+specification_version: 3
+summary: Jakal is a Ruby library for dealing with information overload.
+test_files: []
+